Hacker News new | ask | show | jobs
by fragmede 615 days ago
"seems to" isn't good enough, especially since it's entirely possible to generate code that doesn't give the right answer. 4o is able to write some bad code, run it, recognize that it's bad, and then fix it, if you tell it to.

https://chatgpt.com/share/670086ed-67bc-8009-b96c-39e539791f...
1 comments
Chinjut 615 days ago
Did you actually run the "fixed" code here? Its output is an empty list, just like the pre-"fixed" code.
link
Chinjut 614 days ago
Hm, actually, it's confusing, because clicking the [>_] links where it mentions running code gives different code than it just mentioned.
link